Analyse Virtual Agent NLU performance — conversation completion rates and fallback metrics
AI agents call ml_virtual_agent_nlu to retrieve information from ServiceNow-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes performance metrics from the Virtual Agent NLU system. It is a read-only operation that queries existing data (completion rates, fallback metrics) for analysis purposes. There are no side effects, no data modifications, no code execution, no deletions, and no financial implications.
From the tool's definition The tool description states it 'Analyse Virtual Agent NLU performance — conversation completion rates and fallback metrics', indicating retrieval and analysis of performance data without modifying or executing actions.
Attacks that exploit this kind of access
Analyse Virtual Agent NLU performance — conversation completion rates and fallback metrics. It is categorised as a Read tool in the ServiceNow-MCP MCP Server, which means it retrieves data without modifying state.
Register the ServiceNow- MCP server in PolicyLayer and add a rule for ml_virtual_agent_nlu: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches ServiceNow-MCP. Nothing to install.
ml_virtual_agent_nlu is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the ml_virtual_agent_nlu rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for ml_virtual_agent_nlu. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
ml_virtual_agent_nlu is provided by the ServiceNow- MCP server (tedorigawa001/servicenow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →